Title :
Problem and Strategy: Overfitting in Recurrent Cycles of Internal Symmetry Networks by Back Propagation
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of New South Wales, Sydney, NSW, Australia
Abstract :
Overfitting is an important topic in Neural Network. Internal Symmetry Networks are a new modern Cellular Neural Networks inspired by the phenomenon of internal symmetry in quantum physics. Recurrent Internal Symmetry Networks are just studied very recently. In this paper, overfitting in recurrent cycles of Internal Symmetry Networks is analyzed. Back propagation is trained for an image processing task.
Keywords :
backpropagation; cellular neural nets; recurrent neural nets; back propagation neural nets; cellular neural networks; image processing task; internal symmetry networks recurrent cycles; quantum physics; Australia; Cellular neural networks; Computational intelligence; Computer networks; Computer science; Lattices; Neural networks; Physics; Recurrent neural networks; Reflection; cellular neural networks; dynamic; group representations; internal symmetry; overfitting; recurrent cycle;
Conference_Titel :
Computational Intelligence and Natural Computing, 2009. CINC '09. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3645-3
DOI :
10.1109/CINC.2009.258
